Back to Models

Qwen3 30b a3b instruct 2507

Qwen3 30B Instruct is a MoE model (30.5B total, 3.3B active). It offers strong instruction following and multilingual capabilities.

Parameters
30500000000 B
Context
262,144 tokens
Released
Jan 7, 2025

Leaderboards

Performance vs. Industry Average

Intelligence

Qwen3 30b a3b instruct 2507 is of higher intelligence compared to average (4.1), with an intelligence score of 4.2.

Price

Qwen3 30b a3b instruct 2507 is cheaper compared to average ($1.68 per 1M Tokens) with a price of $0.05 per 1M Tokens.

Latency

Qwen3 30b a3b instruct 2507 has a lower average latency compared to average (53.05s), with an average latency of 37.56s.

P99 Latency

Qwen3 30b a3b instruct 2507 has a lower P99 latency compared to average (187.12s), taking 131.29s to receive the first token at P99 (TTFT).

Context Window

Qwen3 30b a3b instruct 2507 has a smaller context window than average (339k tokens), with a context window of 262k tokens.

Qwen3 30b a3b instruct 2507 - AutoBench